140 likes | 250 Views
A Pareto Frontier for Optimizing Data Transfer vs. Job Execution in Grids. Javid Taheri | Postdoctoral Research Fellow. Albert Y. Zomaya | Professor and Director. Centre for Distributed and High Performance Computing School of Information Technologies
E N D
A Pareto Frontier for Optimizing Data Transfer vs. Job Execution in Grids Javid Taheri | Postdoctoral Research Fellow Albert Y. Zomaya| Professor and Director Centre for Distributed and High Performance Computing School of Information Technologies The University of Sydney, Sydney, Australia
Introduction to Grid Computing • Problem Statement: Data-Aware Job Scheduling • GA-ParFnt • Pareto Frontier • Genetic Algorithm (GA) • Simulation and Analysis of Results • Conclusion
Problem Statement • Data Aware Job Scheduling (DAJS) • (1) the overall execution time of a batch of jobs (NP-Complete) • (2) transfer time of all datafiles to their dependent jobs(NP-Complete) Computation Nodes Storage Nodes File 1 Job 1 File 2 Job 2 File 3 Job 3 ... ... Job N File M
Problem Statement (cont.) SN CN Scheduler SN CN SN CN
Preliminaries • Pareto Front • Genetic Algorithm
Simulation • Test-Grid-4-8
Discussion and Analysis • The shape of Pareto Front Test-Grid-8-4
Discussion and Analysis • Scheduling Algorithms
Conclusion • GA-ParFnt was effective in finding the Pareto Front of executing jobs vs Transfer time of Datafiles in Grids • Such Pareto Front could be estimated by exponential funcitons • Many scheduling algorithms are not optimal, despite their claim.
THANK YOU Questions?